Dynamic Process Maturity Prediction Using AI-Based Engineering Analytics

Abstract

Software-defined vehicle development programs operate in highly dynamic environments where process capability directly influences product quality, safety, compliance, and delivery performance. Traditional process assessments such as ASPICE are periodic and retrospective, limiting the ability of organizations to proactively manage process maturity. This paper proposes a Dynamic Process Maturity Prediction framework based on AI-driven engineering analytics. The framework integrates engineering data from requirements management, configuration management, testing, change management, defect tracking, and quality assurance repositories. Machine-learning models are applied to continuously estimate process capability and predict future maturity trends. The framework enables proactive governance, early identification of capability degradation, and targeted improvement actions. A Software-Defined Vehicle case study demonstrates the applicability of the approach. Experimental results show that predictive analytics can identify maturity risks significantly earlier than conventional audit-based approaches. The proposed framework supports continuous compliance, digital quality management, and data-driven process optimization.